检索结果-南通市图书馆

Deep Reinforcement Learning for Power System Applications: An Overview

在线全文

学校读者我要写书评

暂无评论

cSEE Journal of Power and Energy Systems 2020年第1期6卷 213-225页

作者： Zidong Zhang Dongxia Zhang robert c.qiu Research center For Big Data Engineering And Technologies Shanghai Jiao Tong UniversityShanghai 200240China Department of Electrical and computer Engineering Tennessee Technological UniversityCookevilleTN 38505USA china Electric Power Research Institute Beijing 100192China

Due to increasing complexity, uncertainty and data dimensions in power systems, conventional methods often meet bottlenecks when attempting to solve decision and control prob- lems. Therefore, data-driven methods toward solving such prob- lems are being extensively studied. Deep reinforcement learning (DRL) is one of these data-driven methods and is regarded as real artificial intelligence (AI). DRL is a combination of deep learning (DL) and reinforcement learning (RL). This field of research has been applied to solve a wide range of complex sequential decision-making problems, including those in power systems. This paper firstly reviews the basic ideas, models, algorithms and techniques of DRL. Applications in power systems such as energy management, demand response, electricity market, operational control, and others are then considered. In addition, recent advances in DRL including the combination of RL with other classical methods, and the prospect and challenges of applications in power systems are also discussed.

关键词： Artificial intelligence deep reinforcement learning machine learning power system smart grids

Detection and classification of Transmission Line Transient Faults Based on Graph convolutional Neural Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

cSEE Journal of Power and Energy Systems 2021年第3期7卷 456-471页

作者： Houjie Tong robert c.qiu Dongxia Zhang Haosen Yang Qi Ding Xin Shi Department of Electrical Engineering Center for Big Data and Artificial IntelligenceShanghai Jiao Tong UniversityShanghai 200240China School of Electronic Information and communication Huazhong University of Science and TechnologyWuhan 430000China Electric Power Research Institute Haidian DistrictBeijing 100192China School of control and computer Engineering North China Electric Power UniversityBeijing 102206China

We present a novel transient fault detection and classification approach in power transmission lines based on graph convolutional neural *** with the existing techniques,the proposed approach considers explicit spatial information in sampling sequences as prior knowledge and it has stronger feature extraction *** this basis,a framework for transient fault detection and classification is *** structure is generated to provide topology information to the *** approach takes the adjacency matrix of topology graph and the bus voltage signals during a sampling period after transient faults as inputs,and outputs the predicted classification results ***,the proposed approach is tested in various situations and its generalization ability is verified by experimental *** results show that the proposed approach can detect and classify transient faults more effectively than the existing techniques,and it is practical for online transmission line protection for its rapidness,high robustness and generalization ability.

关键词： Graph convolutional network(GcN) power transmission line fault detection and classification spatio-temporal data topology information

An Accurate and Real-time Method of Self-blast Glass Insulator Location Based on Faster R-cNN and U-net with Aerial Images

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

cSEE Journal of Power and Energy Systems 2019年第4期5卷 474-482页

作者： Zenan Ling Dongxia Zhang robert c.qiu Zhijian Jin Yuhang Zhang Xing He Haichun Liu Department of Electrical Engineering Center for Big Data and Artificial IntelligenceState Energy Smart Grid Research and Development CenterShanghai Jiao Tong UniversityShanghai 200240China china Electric Power Research Institute Beijing 100192China Department of Electrical and computer Engineering Tennessee Technological UniversityCookevilleTN 38505USA

This paper proposes a new deep learning framework for the location of broken insulators(in particular the self-blast glass insulator)in aerial *** address the broken insulators location problem in a low signal-noise-ratio(SNR)*** deal with two modules:1)object detection based on Faster R-cNN,and 2)classification of pixels based on *** the first time,our paper combines the above two *** combination is motivated as follows:Faster R-cNN is used to improve SNR,while the U-net is used for classification of pixels.A diverse aerial image set measured by a power grid in china is tested to validate the proposed ***,a comparison is made among different methods and the result shows that our approach is accurate in real time.

关键词： Aerial images deep learning faster R-cNN insulators location real-time U-net

Achieving superior strength-ductility synergy in a heterostructured magnesium alloy via low-temperature extrusion and low-temperature annealing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2023年第32期163卷 32-44页

作者： H.Wang D.T.Zhang c.qiu W.W.Zhang D.L.chen Guangdong Key Laboratory for Advanced Metallic Materials Processing and Forming National Engineering Research Center of Near-net-shape Forming for Metallic MaterialsSouth China University of TechnologyGuangzhou 510640China Department of Mechanical and Industrial Engineering Toronto Metropolitan University(formerly Ryerson University)350 Victoria StreetTorontoON M5B 2K3Canada

A low-alloyed Mg-1.2Zn-0.1ca(wt.%)alloy was fabricated via low-temperature extrusion and annealing at 250℃for different times(10,30,and 90 min)to attain heterostructures with different fine-grained fractions,focusing on the effect of heterostructure on the mechanical *** dynamic recrystallization(RX)occurred during extrusion at 150℃,and a lamellar structure consisting of fine RX grains and coarse unRX grains was *** subsequent annealing promoted static RX in the as-extruded alloy,leading to an increased fine-grained fraction from 67%to 95%.Meanwhile,the co-segregation of Zn and ca atoms impeded the migration of grain boundaries,thus achieving a fine grain size of 0.8–1.6μ*** sample annealed for 10 min with a fine-grained fraction of 73%and an average RX grain size of 0.9μm exhibited a superior combination of high yield strength(305 MPa)and good ductility(20%).In comparison,an excellent elongation of 30%was achieved in the alloy with a nearly fully-RXed microstructure and an average grain size of 1.6μm after 90 min annealing,despite a lower yield strength of 228 *** unRX grains,the hard orientation with(01–10)parallel to the extrusion direction and high-density dislocations made it more difficult to deform compared with the RX grains,thus producing hetero-deformation induced(HDI)*** fine grains and high-density dislocations,HDI strengthening is the key to achieving the superior mechanical properties of the low-alloyed Mg alloy.

关键词： Low-alloyed magnesium alloy Low-temperature extrusion Annealing Heterostructure Mechanical properties

AAV2-PDE6B restores retinal structure and function in the retinal degeneration 10 mouse model of retinitis pigmentosa by promoting phototransduction and inhibiting apoptosis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第8期20卷 2408-2419页

作者： Ruiqi qiu Mingzhu Yang Xiuxiu Jin Jingyang Liu Weiping Wang Xiaoli Zhang Jinfeng Han Bo Lei Henan Eye Hospital Henan Provincial People’s HospitalPeople’s Hospital of Zhengzhou UniversityZhengzhouHenan ProvinceChina Eye Institute Henan Academy of Innovations in Medical ScienceZhengzhouHenan ProvinceChina Branch of National clinical Research center for Ocular Disease Henan Provincial People’s HospitalZhengzhouHenan ProvinceChina Academy of Medical Science Zhengzhou UniversityZhengzhouHenan ProvinceChina

Retinitis pigmentosa is a group of inherited diseases that lead to retinal degeneration and photoreceptor cell ***,there is no effective treatment for retinitis pigmentosa caused by PDE6B ***-associated virus(AAV)-mediated gene therapy is a promising strategy for treating retinitis *** aim of this study was to explore the molecular mechanisms by which AAV2-PDE6B rescues retinal *** do this,we injected retinal degeneration 10(rd10)mice subretinally with AAV2-PDE6B and assessed the therapeutic effects on retinal function and structure using dark-and light-adapted electroretinogram,optical coherence tomography,and ***-independent acquisition-mass spectrometry-based proteomic analysis was conducted to investigate protein expression levels and pathway enrichment,and the results from this analysis were verified by real-time polymerase chain reaction and western ***2-PDE6B injection significantly upregulated PDE6βexpression,preserved electroretinogram responses,and preserved outer nuclear layer thickness in rd10 *** expressed proteins between wild-type and rd10 mice were closely related to visual perception,and treating rd10 mice with AAV2-PDE6B restored differentially expressed protein expression to levels similar to those seen in wild-type *** Encyclopedia of Genes and Genome analysis showed that the differentially expressed proteins whose expression was most significantly altered by AAV2-PDE6B injection were enriched in phototransduction ***,the phototransductionrelated proteins Pde6α,Rom1,Rho,Aldh1a1,and Rbp1 exhibited opposite expression patterns in rd10 mice with or without AAV2-PDE6B ***,Bax/Bcl-2,p-ERK/ERK,and p-c-Fos/c-Fos expression levels decreased in rd10 mice following AAV2-PDE6B *** data suggest that AAV2-PDE6B-mediated gene therapy promotes phototransduction and inhibits apoptosis by inhibiting the ERK signaling pathway and upr

关键词： apoptosis AAV2-PDE6B ERK1/2 gene therapy phototransduction proteomics rd10 retinitis pigmentosa

Regulating the oxygen-atom configuration of carbon anode enabling extremely fast-charging potassium-ion hybrid capacitors

在线全文

学校读者我要写书评

暂无评论

Nano Research 2025年第1期18卷 373-381页

作者： Daping qiu Yuehui Wang Lulu Zhang Hang Lei Haizhou Ying Jin Niu Min Li Xuelin Yang Feng Wang Ru Yang Hubei Provincial collaborative Innovation center for New Energy Microgrid College of Electrical Engineering and New EnergyChina Three Gorges UniversityYichang 443002China State Key Laboratory of chemical Resource Engineering Laboratory of Electrochemical Process and Technology for MaterialsBeijing University of Chemical TechnologyBeijing 100029China college of Materials and chemical Engineering China Three Gorges UniversityYichang 443002China

Metal-ion hybrid capacitors,such as potassium-ion hybrid capacitors(PIHcs),are regarded as promising fast-charging energy storage ***,the kinetics mismatch between the battery anode and the capacitive cathode restricts their fastcharging *** constructing carbon anodes with enhanced kinetics is an innovative approach to address this ***,using epigallocatechin gallate with high oxygen content as the precursor,oxygen-enriched carbon materials(OEc)with tunable c=O content are successfully ***,the c=O content of OEc is regulated by adjusting the pyrolysis *** as an anode for PIHcs,OEc-600 with the highest c=O content exhibits an attractive fast-charging specific capacity of 135.2 mAh·g^(-1)at 20 A·g^(-1),along with a superior fast-charging cycling *** theoretical calculations,comprehensive kinetics analysis and in-situ Raman,the positive effects of c=O on the potassium storage capability and reversibility of OEc-600 are ***,PIHcs assembled based on an OEc-600 anode deliver impressive energy/power density of 145.1 Wh·kg^(-1)/45.9 kW·kg^(-1)and superior fast-charging cycling stability with 87.5%of capacity retention over 20,000 cycles at 5 A·g^(-1).This work is anticipated to provide an optional design concept toward the carbon anode for fast-charging PIHcs.

关键词： carbon anode oxygen epigallocatechin gallate potassium-ion hybrid capacitor

Research on big data applications in Global Energy Interconnection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Global Energy Interconnection 2018年第3期1卷 352-357页

作者： Dongxia Zhang robert caiming qiu china Electric Power Research Institute Shanghai Jiao Tong University Tennesse Technological University

construction of Global Energy Interconnection(GEI) is regarded as an effective way to utilize clean energy and it has been a hot research topic in recent years. As one of the enabling technologies for GEI, big data is accompanied with the sharing, fusion and comprehensive application of energy related data all over the world. The paper analyzes the technology innovation direction of GEI and the advantages of big data technologies in supporting GEI development, and then gives some typical application scenarios to illustrate the application value of big data. Finally, the architecture for applying random matrix theory in GEI is presented.

关键词： Global Energy Interconnection Big data clean energy Random matrix theory

同方期刊数据库

Genome–Phenome Wide Association in Maize and Arabidopsis Identifies a common Molecular and Evolutionary Signature

在线全文

学校读者我要写书评

暂无评论

Molecular Plant 2020年第6期13卷 907-922页

作者： Zhikai Liang Yumou qiu James c.Schnable Department of Agronomy and Horticulture University of Nebraska-LincolnLincolnNEUSA Plant Science Innovation center University of Nebraska-LincolnLincolnNEUSA Department of Statistics Iowa State UniversityAmesIAUSA

Linking natural genetic variation to trait variation can help determine the functional roles ofdifferent *** of one or several traits are often assessed ***-throughput phenotyping and data mining can capture dozens or hundreds of traits from the same ***,we test the association between markers within a gene and many traits *** genome–phenome wide association study(GPWAS)is both a multi-marker and multi-trait *** identified using GPWAS with 260 phenotypic traits in maize were enriched for genes independently linked to phenotypic *** associated with classical mutants were consistent with reported phenotypes for mutant *** linked to phenomic variation in maize using GPWAS shared molecular,population genetic,and evolutionary features with classical mutants in *** linked to phenomic variation in Arabidopsis using GPWAS are significantly enriched in genes with known loss-of-function *** may be an effective strategy to identify genes in which loss-of-function alleles produce mutant *** shared signatures present in classical mutants and genes identified using GPWAS may be markers for genes with a role in specifying plant phenotypes generally or pleiotropy specifically.

关键词： quantitative genetics phenomics genome-wide association studies mutant phenotypes maize Arabidopsis

A mechanistic study of cO removal on a small H-saturated platinum cluster

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science china chemistry 2008年第12期51卷 1187-1196页

作者： FORREY robert c Department of Physics Pennsylvania State University Berks Campus Reading PA 19610 USA

cO poisoning to platinum catalysts has long been recognized as one of the major technical obstacles in heterogeneous catalysis and its successful removal represents a significant challenge to a wide variety of applications. Using density functional theory (DFT), we performed systematic theoretical calcula-tions to explore the cO removal mechanisms, in the presence of hydrogen, via oxidation by oxygen to form cO2 or reduction by hydrogen to form formaldehyde using a subnano Pt cluster as a model for catalyst nanoparticles. We show that cO oxidation is both thermochemically and kinetically difficult at low H coverage but becomes very exothermic with a moderate activation barrier at high H coverage, suggesting that the oxidation can be carried out readily at elevated temperatures. Doping the Pt cluster with Ru can significantly improve the oxidation thermochemical energy and moderately reduce the activation barrier. The results are consistent with experimental observations. We found that cO reduction by hydrogen to form formaldehyde is moderately endothermic. However, the reaction is predicted to be kinetically difficult due to the relatively high activation barriers associated with the sequential H attacks to the cO molecule.

关键词： cluster Pt-Au alloy full H-saturation cO oxidation cO hydrogenation density functional theory